regex.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'<br><font color=\"red\">ya</font>-<strong>que</strong>-ll<font color=\"red\">aa</font>-pa-<strong>ci</strong>-ble-<strong>cal</strong>-ma-co-<strong>bro</strong>-nes-<strong>bui</strong>-tres   ----&gt;  (13 sílabas, ritmo: 2,5,7,10,12). Rima con \"itres\".<ul><li>  (verso alejandrino a la francesa [2,6,7,10,12][∪–∪∪∪––∪∪–∪–], coincidencia 79%).</li></ul><br><br><br><h2>Resultado final del análisis poético</h2><br><strong>Análisis de estrofas (esquema métrico):</strong> <ul><li>A</li><li>13A</li><li>Contiene 1 versos.</li></ul><br><br><strong>Tipos de estrofa que coinciden con nuestra base de datos:</strong><br><ul><li><font color=\"#088A29\">Verso único y no forma parte de un poema, pero es usado en proverbios, lemas, títulos, etc.</font> Su esquema métrico es A, la coincidencia es del <font color=\"green\"><strong>100%.</strong></font></li></ul><br><br> </br></br></br></br></br></br></br></br></br></br>'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a = '<br><font color=\"red\">ya</font>-<strong>que</strong>-ll<font color=\"red\">aa</font>-pa-<strong>ci</strong>-ble-<strong>cal</strong>-ma-co-<strong>bro</strong>-nes-<strong>bui</strong>-tres   ----&gt;  (13 sílabas, ritmo: 2,5,7,10,12). Rima con \"itres\".<ul><li>  (verso alejandrino a la francesa [2,6,7,10,12][∪–∪∪∪––∪∪–∪–], coincidencia 79%).</li></ul><br><br><br><h2>Resultado final del análisis poético</h2><br><strong>Análisis de estrofas (esquema métrico):</strong> <ul><li>A</li><li>13A</li><li>Contiene 1 versos.</li></ul><br><br><strong>Tipos de estrofa que coinciden con nuestra base de datos:</strong><br><ul><li><font color=\"#088A29\">Verso único y no forma parte de un poema, pero es usado en proverbios, lemas, títulos, etc.</font> Su esquema métrico es A, la coincidencia es del <font color=\"green\"><strong>100%.</strong></font></li></ul><br><br> </br></br></br></br></br></br></br></br></br></br>'\n",
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['13']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import re\n",
    "p = re.compile(r'(?P<uno>\\d+) sílabas')\n",
    "n = p.findall(a)\n",
    "n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['br',\n",
       " 'font color=\"red\"',\n",
       " '/font',\n",
       " 'strong',\n",
       " '/strong',\n",
       " 'font color=\"red\"',\n",
       " '/font',\n",
       " 'strong',\n",
       " '/strong',\n",
       " 'strong']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p = re.compile(r'\\<(.+?)\\>')\n",
    "n = p.findall(a)\n",
    "n[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['red', 'red', '#088A29', 'green']"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p = re.compile(r'color\\=\\\"(.+?)\\\"')\n",
    "n = p.findall(str(a))\n",
    "n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<_sre.SRE_Match object; span=(0, 908), match='<br><font color=\"red\">ya</font>-<strong>que</stro>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n = re.match(r\".+088A29.+\",a)\n",
    "n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<_sre.SRE_Match object; span=(0, 12), match='Isaac Newton'>\n",
      "Isaac\n",
      "Newton\n"
     ]
    }
   ],
   "source": [
    "m = re.match(r\"(\\w+) (\\w+)\", \"Isaac Newton, physicist\")\n",
    "print(m)\n",
    "print(m.group(1))\n",
    "print(m.group(2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<_sre.SRE_Match object; span=(0, 16), match='Malcolm Reynolds'>\n",
      "Malcolm\n",
      "Reynolds\n"
     ]
    }
   ],
   "source": [
    "m = re.match(r\"(?P<first_name>\\w+) (?P<last_name>\\w+)\", \"Malcolm Reynolds Rivera\")\n",
    "print(m)\n",
    "print(m.group('first_name'))\n",
    "print(m.group('last_name'))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Malcolm', 'Reynolds', 'Rivera']\n"
     ]
    }
   ],
   "source": [
    "m = re.findall(r\"(\\w+)\", \"Malcolm Reynolds Rivera\")\n",
    "print(m)\n",
    "# print(m.group('first_name'))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}